Hard exudate detection in retinal fundus images using supervised learning
- PDF / 2,936,536 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 48 Downloads / 257 Views
(0123456789().,-volV)(0123456789(). ,- volV)
GREEN AND HUMAN INFORMATION TECHNOLOGY 2019
Hard exudate detection in retinal fundus images using supervised learning Nipon Theera-Umpon1,2,3
•
Ittided Poonkasem1 • Sansanee Auephanwiriyakul1,3,4 • Direk Patikulsila5
Received: 23 April 2019 / Accepted: 30 July 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract The patients with diabetes have a chance to develop diabetic retinopathy (DR) which affects to the eyes. DR can cause blindness if the patients do not control diabetes. The patients with DR will have an impairment of metabolism of glucose causing a high glucose level in blood vessel called hyperglycemia. It leads to abnormal blood vessel and ultimately results in leakage of blood or fluid like lipoproteins, which are deposited under macular edema called hard exudates. They are normally white or yellowish-white with margins. Hard exudates are often arranged in clumps or circinate rings and located in the outer layer of the retina. The aim of this research was to detect hard exudates by applying several image processing techniques and classify them by using supervised learning methods including support vector machines and some neural network approaches, i.e., multilayer perceptron (MLP) network, hierarchical adaptive neurofuzzy inference system (hierarchical ANFIS), and convolutional neuron networks. DIARETDB1 which contains 89 fundus images is exploited as a dataset for evaluation. Hard exudate candidates are extracted by morphological techniques and classified by the classifiers trained by extracted patches with the corresponding ground truths. The tenfold cross-validation is applied to assure the generalization of the results. The proposed method achieves the area under the curve (AUC) of 0.998 when the MLP network is applied. The AUCs for all four classifiers are more than 0.95. This shows that the combination of image processing techniques and suitable classifiers can perform very well in hard exudate detection problem. Keywords Diabetic retinopathy Hard exudates Fundus image Multilayer perceptron network Support vector machine Hierarchical adaptive neurofuzzy inference system Convolutional neural networks
1 Introduction
& Nipon Theera-Umpon [email protected]; [email protected] 1
Biomedical Engineering Institute, Chiang Mai University, Chiang Mai 50200, Thailand
2
Department of Electrical Engineering, Faculty of Engineering, Chiang Mai University, Chiang Mai, Thailand
3
Excellence Center in Infrastructure Technology and Transportation Engineering, Chiang Mai University, Chiang Mai, Thailand
4
Department of Computer Engineering, Faculty of Engineering, Chiang Mai University, Chiang Mai, Thailand
5
Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand
Diabetes mellitus (DM) is an impairment of metabolism of glucose caused by insulin deficiency or its resistance leading to hyperglycemia. This may finally result in vascular and neuropathic complications. People with diabetes ca
Data Loading...
